Hidden Thoughts Collection Chain-of-thought that hides what the model is really doing: cheating without saying so, latent soft-token, and filler-token reasoning. • 3 items • Updated 1 day ago
Hidden Thoughts Collection Chain-of-thought that hides what the model is really doing: cheating without saying so, latent soft-token, and filler-token reasoning. • 3 items • Updated 1 day ago
Hidden Thoughts Collection Chain-of-thought that hides what the model is really doing: cheating without saying so, latent soft-token, and filler-token reasoning. • 3 items • Updated 1 day ago